{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/llama/papers/8","list_of":"/method/llama","method":"LLaMA","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":8,"pages_in_order":11,"rows_per_page":100,"rows":[701,800],"of":1062,"counts":{"archive_papers_tagged":1062,"with_a_code_link":423,"where_syntology_ran_a_sample":143,"not_listed_spam_title":0,"listed":1062,"listed_where_code_ran":143,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":127,"every_run_a_failure_of_syntologys_instrument":16,"listed_with_a_run_with_no_instrument_failure":127,"listed_every_run_a_failure_of_syntologys_instrument":16,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/llama","prev":"/method/llama/papers/7","next":"/method/llama/papers/9","papers":[{"paper":null,"slug":"membership-inference-attacks-against-in","title":"Membership Inference Attacks Against In-Context Learning","date":"2024-09-02","arxiv_id":"2409.01380","n_code_links":0,"syntology":null},{"paper":"/paper/assessing-generative-language-models-in","slug":"assessing-generative-language-models-in","title":"Assessing Generative Language Models in Classification Tasks: Performance and Self-Evaluation Capabilities in the Environmental and Climate Change Domain","date":"2024-08-30","arxiv_id":"2408.17362","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-large-language-models-address-open-target","title":"Can Large Language Models Address Open-Target Stance Detection?","date":"2024-08-30","arxiv_id":"2409.00222","n_code_links":0,"syntology":null},{"paper":"/paper/training-ultra-long-context-language-model","slug":"training-ultra-long-context-language-model","title":"Training Ultra Long Context Language Model with Fully Pipelined Distributed Transformer","date":"2024-08-30","arxiv_id":"2408.16978","n_code_links":1,"syntology":null},{"paper":"/paper/cbf-llm-safe-control-for-llm-alignment","slug":"cbf-llm-safe-control-for-llm-alignment","title":"CBF-LLM: Safe Control for LLM Alignment","date":"2024-08-28","arxiv_id":"2408.15625","n_code_links":1,"syntology":null},{"paper":"/paper/harmonized-speculative-sampling","slug":"harmonized-speculative-sampling","title":"Learning Harmonized Representations for Speculative Sampling","date":"2024-08-28","arxiv_id":"2408.15766","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-of-large-language-models-for-3","title":"A Survey of Large Language Models for European Languages","date":"2024-08-27","arxiv_id":"2408.15040","n_code_links":0,"syntology":null},{"paper":null,"slug":"evidence-enhanced-triplet-generation","title":"Evidence-Enhanced Triplet Generation Framework for Hallucination Alleviation in Generative Question Answering","date":"2024-08-27","arxiv_id":"2408.15037","n_code_links":0,"syntology":null},{"paper":"/paper/gift-sw-gaussian-noise-injected-fine-tuning","slug":"gift-sw-gaussian-noise-injected-fine-tuning","title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","date":"2024-08-27","arxiv_id":"2408.15300","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["On-Point-RND/GIFT_SW"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/wait-that-s-not-an-option-llms-robustness","slug":"wait-that-s-not-an-option-llms-robustness","title":"Wait, that's not an option: LLMs Robustness with Incorrect Multiple-Choice Options","date":"2024-08-27","arxiv_id":"2409.00113","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gracjangoral/when-all-options-are-wrong"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-language-and-large-language-model","slug":"vision-language-and-large-language-model","title":"Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models","date":"2024-08-25","arxiv_id":"2409.00084","n_code_links":1,"syntology":null},{"paper":"/paper/discovering-long-term-effects-on-parameter","slug":"discovering-long-term-effects-on-parameter","title":"SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning","date":"2024-08-24","arxiv_id":"2409.06706","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":6,"n_instrument":1,"unverified":3,"pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["daviddaiiiii/san-peft"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/speechcraft-a-fine-grained-expressive-speech","slug":"speechcraft-a-fine-grained-expressive-speech","title":"SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language Description","date":"2024-08-24","arxiv_id":"2408.13608","n_code_links":1,"syntology":null},{"paper":null,"slug":"instruct-deberta-a-hybrid-approach-for-aspect","title":"Instruct-DeBERTa: A Hybrid Approach for Aspect-based Sentiment Analysis on Textual Reviews","date":"2024-08-23","arxiv_id":"2408.13202","n_code_links":0,"syntology":null},{"paper":"/paper/memory-efficient-llm-training-with-online","slug":"memory-efficient-llm-training-with-online","title":"Memory-Efficient LLM Training with Online Subspace Descent","date":"2024-08-23","arxiv_id":"2408.12857","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":3,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kyleliang919/online-subspace-descent"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-evaluating-and-building-versatile","slug":"towards-evaluating-and-building-versatile","title":"Towards Evaluating and Building Versatile Large Language Models for Medicine","date":"2024-08-22","arxiv_id":"2408.12547","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["magic-ai4med/meds-ins"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cipher-cybersecurity-intelligent-penetration","slug":"cipher-cybersecurity-intelligent-penetration","title":"CIPHER: Cybersecurity Intelligent Penetration-testing Helper for Ethical Researcher","date":"2024-08-21","arxiv_id":"2408.11650","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-detection-of-toxic-prompts-in-large","title":"Efficient Detection of Toxic Prompts in Large Language Models","date":"2024-08-21","arxiv_id":"2408.11727","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-pruning-and-distillation-in-practice-the","title":"LLM Pruning and Distillation in Practice: The Minitron Approach","date":"2024-08-21","arxiv_id":"2408.11796","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-large-language-models-for-math","slug":"benchmarking-large-language-models-for-math","title":"Benchmarking Large Language Models for Math Reasoning Tasks","date":"2024-08-20","arxiv_id":"2408.10839","n_code_links":1,"syntology":null},{"paper":"/paper/ferret-faster-and-effective-automated-red","slug":"ferret-faster-and-effective-automated-red","title":"Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique","date":"2024-08-20","arxiv_id":"2408.10701","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-a-local-llama-3-large-language","title":"Fine-Tuning a Local LLaMA-3 Large Language Model for Automated Privacy-Preserving Physician Letter Generation in Radiation Oncology","date":"2024-08-20","arxiv_id":"2408.10715","n_code_links":0,"syntology":null},{"paper":"/paper/language-modeling-on-tabular-data-a-survey-of","slug":"language-modeling-on-tabular-data-a-survey-of","title":"Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolution","date":"2024-08-20","arxiv_id":"2408.10548","n_code_links":1,"syntology":null},{"paper":"/paper/llm-barber-block-aware-rebuilder-for-sparsity","slug":"llm-barber-block-aware-rebuilder-for-sparsity","title":"LLM-Barber: Block-Aware Rebuilder for Sparsity Mask in One-Shot for Large Language Models","date":"2024-08-20","arxiv_id":"2408.10631","n_code_links":1,"syntology":null},{"paper":"/paper/revisiting-verilogeval-newer-llms-in-context","slug":"revisiting-verilogeval-newer-llms-in-context","title":"Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code Generation","date":"2024-08-20","arxiv_id":"2408.11053","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nvlabs/verilog-eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/fine-tuning-llms-for-autonomous-spacecraft","slug":"fine-tuning-llms-for-autonomous-spacecraft","title":"Fine-tuning LLMs for Autonomous Spacecraft Control: A Case Study Using Kerbal Space Program","date":"2024-08-16","arxiv_id":"2408.08676","n_code_links":1,"syntology":null},{"paper":"/paper/the-fellowship-of-the-llms-multi-agent","slug":"the-fellowship-of-the-llms-multi-agent","title":"The Fellowship of the LLMs: Multi-Agent Workflows for Synthetic Preference Optimization Dataset Generation","date":"2024-08-16","arxiv_id":"2408.08688","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-the-capabilities-of-large","title":"Benchmarking the Capabilities of Large Language Models in Transportation System Engineering: Accuracy, Consistency, and Reasoning Behaviors","date":"2024-08-15","arxiv_id":"2408.08302","n_code_links":0,"syntology":null},{"paper":"/paper/cybench-a-framework-for-evaluating","slug":"cybench-a-framework-for-evaluating","title":"Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models","date":"2024-08-15","arxiv_id":"2408.08926","n_code_links":3,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["andyzorigin/cybench","andyzorigin/cyber-bench"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/i-sheep-self-alignment-of-llm-from-scratch","slug":"i-sheep-self-alignment-of-llm-from-scratch","title":"I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm","date":"2024-08-15","arxiv_id":"2408.08072","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["multimodal-art-projection/I-SHEEP"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"jpeg-lm-llms-as-image-generators-with","title":"JPEG-LM: LLMs as Image Generators with Canonical Codec Representations","date":"2024-08-15","arxiv_id":"2408.08459","n_code_links":0,"syntology":null},{"paper":null,"slug":"mgh-radiology-llama-a-llama-3-70b-model-for","title":"MGH Radiology Llama: A Llama 3 70B Model for Radiology","date":"2024-08-13","arxiv_id":"2408.11848","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-advanced-llms-to-enhance-smaller-llms","title":"Using Advanced LLMs to Enhance Smaller LLMs: An Interpretable Knowledge Distillation Approach","date":"2024-08-13","arxiv_id":"2408.07238","n_code_links":0,"syntology":null},{"paper":null,"slug":"lut-tensor-core-lookup-table-enables","title":"LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference","date":"2024-08-12","arxiv_id":"2408.06003","n_code_links":0,"syntology":null},{"paper":"/paper/eigen-attention-attention-in-low-rank-space","slug":"eigen-attention-attention-in-low-rank-space","title":"Eigen Attention: Attention in Low-Rank Space for KV Cache Compression","date":"2024-08-10","arxiv_id":"2408.05646","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":7,"n_instrument":2,"unverified":4,"pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["utkarshsaxena1/eigenattn"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"llama-based-punctuation-restoration-with","title":"LLaMA based Punctuation Restoration With Forward Pass Only Decoding","date":"2024-08-09","arxiv_id":"2408.11845","n_code_links":0,"syntology":null},{"paper":"/paper/bias-aware-low-rank-adaptation-mitigating","slug":"bias-aware-low-rank-adaptation-mitigating","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","date":"2024-08-08","arxiv_id":"2408.04556","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":10,"n_instrument":2,"unverified":1,"pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cyp-jlu-ai/ba-lora"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-comparison-of-llm-finetuning-methods","title":"A Comparison of LLM Finetuning Methods & Evaluation Metrics with Travel Chatbot Use Case","date":"2024-08-07","arxiv_id":"2408.03562","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-convex-optimization-based-layer-wise-post","title":"A Convex-optimization-based Layer-wise Post-training Pruner for Large Language Models","date":"2024-08-07","arxiv_id":"2408.03728","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-02201","title":"Evaluating the Performance of Large Language Models for SDG Mapping (Technical Report)","date":"2024-08-05","arxiv_id":"2408.02201","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-02237","title":"Do Large Language Models Speak All Languages Equally? A Comparative Study in Low-Resource Settings","date":"2024-08-05","arxiv_id":"2408.02237","n_code_links":0,"syntology":null},{"paper":"/paper/2408-02056","slug":"2408-02056","title":"MedSyn: LLM-based Synthetic Medical Text Generation Framework","date":"2024-08-04","arxiv_id":"2408.02056","n_code_links":1,"syntology":null},{"paper":null,"slug":"2408-01866","title":"Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlessly","date":"2024-08-03","arxiv_id":"2408.01866","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficacy-of-large-language-models-in","title":"Efficacy of Large Language Models in Systematic Reviews","date":"2024-08-03","arxiv_id":"2408.04646","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-01605","title":"CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models","date":"2024-08-02","arxiv_id":"2408.01605","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-comes-after-transformers-a-selective","title":"What comes after transformers? -- A selective survey connecting ideas in deep learning","date":"2024-08-01","arxiv_id":"2408.00386","n_code_links":0,"syntology":null},{"paper":null,"slug":"2407-21330","title":"Performance of Recent Large Language Models for a Low-Resourced Language","date":"2024-07-31","arxiv_id":"2407.21330","n_code_links":0,"syntology":null},{"paper":null,"slug":"2407-21772","title":"ShieldGemma: Generative AI Content Moderation Based on Gemma","date":"2024-07-31","arxiv_id":"2407.21772","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-00162","title":"A Taxonomy of Stereotype Content in Large Language Models","date":"2024-07-31","arxiv_id":"2408.00162","n_code_links":0,"syntology":null},{"paper":"/paper/the-llama-3-herd-of-models","slug":"the-llama-3-herd-of-models","title":"The Llama 3 Herd of Models","date":"2024-07-31","arxiv_id":"2407.21783","n_code_links":5,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"a2sf-accumulative-attention-scoring-with","title":"A2SF: Accumulative Attention Scoring with Forgetting Factor for Token Pruning in Transformer Decoder","date":"2024-07-30","arxiv_id":"2407.20485","n_code_links":0,"syntology":null},{"paper":null,"slug":"affective-computing-in-the-era-of-large","title":"Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective","date":"2024-07-30","arxiv_id":"2408.04638","n_code_links":0,"syntology":null},{"paper":"/paper/comparison-of-large-language-models-for","slug":"comparison-of-large-language-models-for","title":"Comparison of Large Language Models for Generating Contextually Relevant Questions","date":"2024-07-30","arxiv_id":"2407.20578","n_code_links":1,"syntology":null},{"paper":"/paper/think-thinner-key-cache-by-query-driven","slug":"think-thinner-key-cache-by-query-driven","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","date":"2024-07-30","arxiv_id":"2407.21018","n_code_links":0,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"evaluating-large-language-models-for-3","title":"Evaluating Large Language Models for automatic analysis of teacher simulations","date":"2024-07-29","arxiv_id":"2407.20360","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-directed-synthetic-dialogues-and","title":"Self-Directed Synthetic Dialogues and Revisions Technical Report","date":"2024-07-25","arxiv_id":"2407.18421","n_code_links":0,"syntology":null},{"paper":"/paper/unified-lexical-representation-for","slug":"unified-lexical-representation-for","title":"Unified Lexical Representation for Interpretable Visual-Language Alignment","date":"2024-07-25","arxiv_id":"2407.17827","n_code_links":1,"syntology":null},{"paper":"/paper/accurate-and-efficient-fine-tuning-of","slug":"accurate-and-efficient-fine-tuning-of","title":"Accurate and Efficient Fine-Tuning of Quantized Large Language Models Through Optimal Balance","date":"2024-07-24","arxiv_id":"2407.17029","n_code_links":1,"syntology":null},{"paper":"/paper/data-mixture-inference-what-do-bpe-tokenizers","slug":"data-mixture-inference-what-do-bpe-tokenizers","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","date":"2024-07-23","arxiv_id":"2407.16607","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alisawuffles/tokenizer-attack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/lawma-the-power-of-specialization-for-legal","slug":"lawma-the-power-of-specialization-for-legal","title":"Lawma: The Power of Specialization for Legal Tasks","date":"2024-07-23","arxiv_id":"2407.16615","n_code_links":0,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/decoding-multilingual-moral-preferences","slug":"decoding-multilingual-moral-preferences","title":"Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment","date":"2024-07-21","arxiv_id":"2407.15184","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-context-aware-preference-modeling","title":"Improving Context-Aware Preference Modeling for Language Models","date":"2024-07-20","arxiv_id":"2407.14916","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-databases-improve-success-in","title":"Adversarial Databases Improve Success in Retrieval-based Large Language Models","date":"2024-07-19","arxiv_id":"2407.14609","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatqa-2-bridging-the-gap-to-proprietary-llms","title":"ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities","date":"2024-07-19","arxiv_id":"2407.14482","n_code_links":0,"syntology":null},{"paper":null,"slug":"impact-of-model-size-on-fine-tuned-llm","title":"Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigation","date":"2024-07-19","arxiv_id":"2407.14088","n_code_links":0,"syntology":null},{"paper":null,"slug":"lazyllm-dynamic-token-pruning-for-efficient","title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference","date":"2024-07-19","arxiv_id":"2407.14057","n_code_links":0,"syntology":null},{"paper":"/paper/can-open-source-llms-compete-with-commercial","slug":"can-open-source-llms-compete-with-commercial","title":"Can Open-Source LLMs Compete with Commercial Models? Exploring the Few-Shot Performance of Current GPT Models in Biomedical Tasks","date":"2024-07-18","arxiv_id":"2407.13511","n_code_links":1,"syntology":null},{"paper":"/paper/learning-goal-conditioned-representations-for","slug":"learning-goal-conditioned-representations-for","title":"Learning Goal-Conditioned Representations for Language Reward Models","date":"2024-07-18","arxiv_id":"2407.13887","n_code_links":1,"syntology":null},{"paper":null,"slug":"reconstruct-the-pruned-model-without-any","title":"Reconstruct the Pruned Model without Any Retraining","date":"2024-07-18","arxiv_id":"2407.13331","n_code_links":0,"syntology":null},{"paper":"/paper/text-and-feature-based-models-for-compound","slug":"text-and-feature-based-models-for-compound","title":"Textualized and Feature-based Models for Compound Multimodal Emotion Recognition in the Wild","date":"2024-07-17","arxiv_id":"2407.12927","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nicolas-richet/feature-vs-text-compound-emotion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mini-llm-memory-efficient-structured-pruning","title":"MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models","date":"2024-07-16","arxiv_id":"2407.11681","n_code_links":0,"syntology":null},{"paper":"/paper/spinach-sparql-based-information-navigation","slug":"spinach-sparql-based-information-navigation","title":"SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions","date":"2024-07-16","arxiv_id":"2407.11417","n_code_links":2,"syntology":null},{"paper":null,"slug":"leveraging-llm-respondents-for-item","title":"Leveraging LLM-Respondents for Item Evaluation: a Psychometric Analysis","date":"2024-07-15","arxiv_id":"2407.10899","n_code_links":0,"syntology":null},{"paper":null,"slug":"bilingual-adaptation-of-monolingual","title":"Bilingual Adaptation of Monolingual Foundation Models","date":"2024-07-13","arxiv_id":"2407.12869","n_code_links":0,"syntology":null},{"paper":null,"slug":"muscle-a-model-update-strategy-for-compatible","title":"MUSCLE: A Model Update Strategy for Compatible LLM Evolution","date":"2024-07-12","arxiv_id":"2407.09435","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-two-sides-of-the-coin-hallucination","title":"The Two Sides of the Coin: Hallucination Generation and Detection with LLMs as Evaluators for LLMs","date":"2024-07-12","arxiv_id":"2407.09152","n_code_links":0,"syntology":null},{"paper":null,"slug":"souplm-model-integration-in-large-language","title":"SoupLM: Model Integration in Large Language and Multi-Modal Models","date":"2024-07-11","arxiv_id":"2407.08196","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-estimation-of-large-language","title":"Uncertainty Estimation of Large Language Models in Medical Question Answering","date":"2024-07-11","arxiv_id":"2407.08662","n_code_links":0,"syntology":null},{"paper":"/paper/fsponer-few-shot-prompt-optimization-for","slug":"fsponer-few-shot-prompt-optimization-for","title":"FsPONER: Few-shot Prompt Optimization for Named Entity Recognition in Domain-specific Scenarios","date":"2024-07-10","arxiv_id":"2407.08035","n_code_links":1,"syntology":null},{"paper":null,"slug":"rag-vs-long-context-examining-frontier-large","title":"Examining Long-Context Large Language Models for Environmental Review Document Comprehension","date":"2024-07-10","arxiv_id":"2407.07321","n_code_links":0,"syntology":null},{"paper":null,"slug":"convnlp-image-based-ai-text-detection","title":"ConvNLP: Image-based AI Text Detection","date":"2024-07-09","arxiv_id":"2407.07225","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-comparison-of-vocabulary","slug":"an-empirical-comparison-of-vocabulary","title":"An Empirical Comparison of Vocabulary Expansion and Initialization Approaches for Language Models","date":"2024-07-08","arxiv_id":"2407.05841","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["AI4Bharat/VocabAdaptation_LLM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"empirical-study-of-symmetrical-reasoning-in","title":"Empirical Study of Symmetrical Reasoning in Conversational Chatbots","date":"2024-07-08","arxiv_id":"2407.05734","n_code_links":0,"syntology":null},{"paper":"/paper/llamax-scaling-linguistic-horizons-of-llm-by","slug":"llamax-scaling-linguistic-horizons-of-llm-by","title":"LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages","date":"2024-07-08","arxiv_id":"2407.05975","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["cone-mt/llamax"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/pruning-large-language-models-to-intra-module","slug":"pruning-large-language-models-to-intra-module","title":"Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations","date":"2024-07-08","arxiv_id":"2407.05690","n_code_links":1,"syntology":null},{"paper":"/paper/climb-a-benchmark-of-clinical-bias-in-large","slug":"climb-a-benchmark-of-clinical-bias-in-large","title":"CLIMB: A Benchmark of Clinical Bias in Large Language Models","date":"2024-07-07","arxiv_id":"2407.05250","n_code_links":1,"syntology":null},{"paper":"/paper/sbora-low-rank-adaptation-with-regional","slug":"sbora-low-rank-adaptation-with-regional","title":"SBoRA: Low-Rank Adaptation with Regional Weight Updates","date":"2024-07-07","arxiv_id":"2407.05413","n_code_links":1,"syntology":null},{"paper":"/paper/lora-ga-low-rank-adaptation-with-gradient","slug":"lora-ga-low-rank-adaptation-with-gradient","title":"LoRA-GA: Low-Rank Adaptation with Gradient Approximation","date":"2024-07-06","arxiv_id":"2407.05000","n_code_links":1,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["outsider565/lora-ga"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"statistical-investigations-into-the-geometry","title":"Statistical investigations into the geometry and homology of random programs","date":"2024-07-05","arxiv_id":"2407.04854","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-data-to-commonsense-reasoning-the-use-of","title":"From Data to Commonsense Reasoning: The Use of Large Language Models for Explainable AI","date":"2024-07-04","arxiv_id":"2407.03778","n_code_links":0,"syntology":null},{"paper":"/paper/q-adapter-training-your-llm-adapter-as-a","slug":"q-adapter-training-your-llm-adapter-as-a","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","date":"2024-07-04","arxiv_id":"2407.03856","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":9,"n_instrument":4,"unverified":1,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mansicer/Q-Adapter"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/the-mysterious-case-of-neuron-1512-injectable","slug":"the-mysterious-case-of-neuron-1512-injectable","title":"The Mysterious Case of Neuron 1512: Injectable Realignment Architectures Reveal Internal Characteristics of Meta's Llama 2 Model","date":"2024-07-04","arxiv_id":"2407.03621","n_code_links":1,"syntology":null},{"paper":"/paper/medpix-2-0-a-comprehensive-multimodal","slug":"medpix-2-0-a-comprehensive-multimodal","title":"MedPix 2.0: A Comprehensive Multimodal Biomedical Data set for Advanced AI Applications","date":"2024-07-03","arxiv_id":"2407.02994","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-numeric-awards-in-context-dueling","title":"Beyond Numeric Awards: In-Context Dueling Bandits with LLM Agents","date":"2024-07-02","arxiv_id":"2407.01887","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-bias-building-bridges-evaluation-and","title":"Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis","date":"2024-07-02","arxiv_id":"2407.02030","n_code_links":0,"syntology":null},{"paper":null,"slug":"s2d-sorted-speculative-decoding-for-more","title":"S2D: Sorted Speculative Decoding For More Efficient Deployment of Nested Large Language Models","date":"2024-07-02","arxiv_id":"2407.01955","n_code_links":0,"syntology":null},{"paper":null,"slug":"badllama-3-removing-safety-finetuning-from","title":"Badllama 3: removing safety finetuning from Llama 3 in minutes","date":"2024-07-01","arxiv_id":"2407.01376","n_code_links":0,"syntology":null},{"paper":null,"slug":"calibrated-large-language-models-for-binary","title":"Calibrated Large Language Models for Binary Question Answering","date":"2024-07-01","arxiv_id":"2407.01122","n_code_links":0,"syntology":null},{"paper":"/paper/deciphering-the-factors-influencing-the","slug":"deciphering-the-factors-influencing-the","title":"Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning","date":"2024-07-01","arxiv_id":"2407.01687","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["aksh555/deciphering_cot"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"min-p-sampling-balancing-creativity-and","title":"Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs","date":"2024-07-01","arxiv_id":"2407.01082","n_code_links":0,"syntology":null}],"record_sha256":"27fc77b3847ddc4dde943288e8f050fce81100ee1877f97374ef6c148ead79e9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}